deepcopy of LazyLinear fails

[nicolas-dufour]

🐛 Describe the bug

When running

l_linear = LazyLinear(10)
deepcopy(l_linear)

the following error is triggered

Exception has occurred: TypeError
empty() received an invalid combination of arguments - got (int, dtype=NoneType, device=bool), but expected one of:
 * (tuple of ints size, *, tuple of names names, torch.memory_format memory_format, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of SymInts size, *, torch.memory_format memory_format, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
 * (tuple of ints size, *, torch.memory_format memory_format, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)
  File "/Users/ndufour/Documents/pytorch/rl/debug_deepcopy.py", line 9, in <module>
    deepcopy(l_linear)

This prevents making deepcopy of models before doing forward on one of them

Versions

Collecting environment information...
PyTorch version: 1.13.0.dev20220725
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: macOS 12.5 (arm64)
GCC version: Could not collect
Clang version: 13.1.6 (clang-1316.0.21.2.5)
CMake version: Could not collect
Libc version: N/A

Python version: 3.9.12 (main, Jun 1 2022, 06:34:44) [Clang 12.0.0 ] (64-bit runtime)
Python platform: macOS-12.5-arm64-arm-64bit
Is CUDA available: False
CUDA runtime version: No CUDA
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

Versions of relevant libraries:
[pip3] functorch==0.3.0a0+516a8cd
[pip3] mypy-extensions==0.4.3
[pip3] numpy==1.23.1
[pip3] torch==1.13.0.dev20220725
[pip3] torchrl==0.0.1a0+008bebd
[pip3] torchvision==0.14.0.dev20220725
[conda] functorch 0.3.0a0+516a8cd pypi_0 pypi
[conda] numpy 1.23.1 py39h42add53_0
[conda] numpy-base 1.23.1 py39hadd41eb_0
[conda] pytorch 1.13.0.dev20220725 py3.9_0 pytorch-nightly
[conda] torchrl 0.0.1a0+008bebd dev_0
[conda] torchvision 0.14.0.dev20220725 py39_cpu pytorch-nightly

cc @albanD @mruberry @jbschlosser @walterddr @kshitij12345 @saketh-are

[jbschlosser]

Related: #65051